6 papers
Making Expert Reasoning Learnable with Self-Distillation
Ethan Mendes, Jungsoo Park, Alan Ritter
Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or the existence o…
Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression
Jungsoo Park, Hyungjoo Chae, Ethan Mendes +4
Large language models can predict real-valued quantities from heterogeneous inputs such as text, code, and molecular strings, but most training objectives score each decoded floati…
GeoRC: A Benchmark for Geolocation Reasoning Chains
Mohit Talreja, Joshua Diao, Jim Thannikary James +6
Vision Language Models (VLMs) are good at recognizing the global location of a photograph -- their geolocation prediction accuracy rivals the best human experts. But many VLMs are…
Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?
Ruixin Yang, Ethan Mendes, Arthur Wang +4
Vision-language models (VLMs) have demonstrated strong performance in image geolocation, a capability further sharpened by frontier multimodal large reasoning models (MLRMs). This…
Anticipatory Evaluation of Language Models
Jungsoo Park, Ethan Mendes, Gabriel Stanovsky +1
Progress in large language models is increasingly constrained by an evaluation bottleneck: benchmarks must be built and models run before iteration can begin. We investigate whethe…
Language Models can Self-Improve at State-Value Estimation for Better Search
Ethan Mendes, Alan Ritter
Collecting ground-truth rewards or human demonstrations for multi-step reasoning tasks is often prohibitively expensive, particularly in interactive domains such as web tasks. We i…